Vulnerability of 3D Face Recognition Systems to Morphing Attacks

TL;DR

This paper investigates the vulnerability of 3D face recognition systems to morphing attacks, demonstrating that such systems are susceptible to high-quality 3D face morphs with significant similarity scores, highlighting security concerns.

Contribution

It introduces methods for generating 3D face morphs and evaluates their effectiveness against 3D face recognition systems, an area less explored compared to 2D systems.

Findings

Highest MMPMR of 40% with RMMR of 41.76% against look-a-like morphs

3DFR systems show notable vulnerability to 3D face morphing attacks

Methods for creating 3D face morphs are proposed and tested

Abstract

In recent years face recognition systems have been brought to the mainstream due to development in hardware and software. Consistent efforts are being made to make them better and more secure. This has also brought developments in 3D face recognition systems at a rapid pace. These 3DFR systems are expected to overcome certain vulnerabilities of 2DFR systems. One such problem that the domain of 2DFR systems face is face image morphing. A substantial amount of research is being done for generation of high quality face morphs along with detection of attacks from these morphs. Comparatively the understanding of vulnerability of 3DFR systems against 3D face morphs is less. But at the same time an expectation is set from 3DFR systems to be more robust against such attacks. This paper attempts to research and gain more information on this matter. The paper describes a couple of methods that can be used to generate 3D face morphs. The face morphs that are generated using this method are then compared to the contributing faces to obtain similarity scores. The highest MMPMR is obtained around 40% with RMMR of 41.76% when 3DFRS are attacked with look-a-like morphs.